Fifth generation mobile communication system (5G) mobile operators need to explore new use cases and/or applications together with vertical industries, the industries that are potential users of 5G, in order to fully exploit the new 5G capabilities in terms of its application. Vehicle-to-Everything (V2X) communications for platooning are considered to be one of new 5G use cases whose ultra reliable and low latency communication (URLLC) aspects are required. The authors build a field experimental environment, towards application to truck platooning, with actual large-size trucks and a prototype system, for 5G New Radio (NR) technology based V2X communications. Its most distinctive feature is that the 5G NR-V2X prototype system is equipped with UE-to-UE radio interface (i.e., sidelink) for V2V Direct communication, in addition to the traditional radio interfaces between BS and UE for V2N/V2N2V communications. This paper presents performance evaluation and demonstration of real-time vehicle control information exchange using over the sidelink of 5G NR-V2X prototype system for automated follower truck platooning. This paper evaluates the V2V Direct communication latency and reliability performance of the sidelink, and clarify 5G NR sidelink achieves lower peak of latency and higher packet reception rate in V2V Direct communication performance than an optical wireless communication system product. Then, it also introduces a 5G URLLC use case demonstration of automated follower truck platooning trial employed with the prototype system in a public expressway environment.
Dody ICHWANA PUTRA Muhammad HARRY BINTANG PRATAMA Ryotaro ISSHIKI Yuhei NAGAO Leonardo LANANTE JR Hiroshi OCHI
This paper presents a unified software and hardware wireless AI platform (USHWAP) for developing and evaluating machine learning in wireless systems. The platform integrates multi-software development such as MATLAB and Python with hardware platforms like FPGA and SDR, allowing for flexible and scalable device and edge computing application development. The USHWAP is implemented and validated using FPGAs and SDRs. Wireless signal classification, wireless LAN sensing, and rate adaptation are used as examples to showcase the platform's capabilities. The platform enables versatile development, including software simulation and real-time hardware implementation, offering flexibility and scalability for multiple applications. It is intended to be used by wireless-AI researchers to develop and evaluate intelligent algorithms in a laboratory environment.
Jianbo WANG Haozhi HUANG Li SHEN Xuan WANG Toshihiko YAMASAKI
The image-to-image translation aims to learn a mapping between the source and target domains. For improving visual quality, the majority of previous works adopt multi-stage techniques to refine coarse results in a progressive manner. In this work, we present a novel approach for generating plausible details by only introducing a group of intermediate supervisions without cascading multiple stages. Specifically, we propose a Laplacian Pyramid Transformation Generative Adversarial Network (LapTransGAN) to simultaneously transform components in different frequencies from the source domain to the target domain within only one stage. Hierarchical perceptual and gradient penalization are utilized for learning consistent semantic structures and details at each pyramid level. The proposed model is evaluated based on various metrics, including the similarity in feature maps, reconstruction quality, segmentation accuracy, similarity in details, and qualitative appearances. Our experiments show that LapTransGAN can achieve a much better quantitative performance than both the supervised pix2pix model and the unsupervised CycleGAN model. Comprehensive ablation experiments are conducted to study the contribution of each component.
Fuma SAWA Yoshinori KAMIZONO Wataru KOBAYASHI Ittetsu TANIGUCHI Hiroki NISHIKAWA Takao ONOYE
Advanced driver-assistance systems (ADAS) generally play an important role to support safe drive by detecting potential risk factors beforehand and informing the driver of them. However, if too many services in ADAS rely on visual-based technologies, the driver becomes increasingly burdened and exhausted especially on their eyes. The drivers should be back out of monitoring tasks other than significantly important ones in order to alleviate the burden of the driver as long as possible. In-vehicle auditory signals to assist the safe drive have been appealing as another approach to altering visual suggestions in recent years. In this paper, we developed an in-vehicle auditory signals evaluation platform in an existing driving simulator. In addition, using in-vehicle auditory signals, we have demonstrated that our developed platform has highlighted the possibility to partially switch from only visual-based tasks to mixing with auditory-based ones for alleviating the burden on drivers.
Mashiho MUKAIDA Yoshiaki UEDA Noriaki SUETAKE
Recently, a lot of low-light image enhancement methods have been proposed. However, these methods have some problems such as causing fine details lost in bright regions and/or unnatural color tones. In this paper, we propose a new low-light image enhancement method to cope with these problems. In the proposed method, a pixel is represented by a convex combination of white, black, and pure color. Then, an equi-hue plane in RGB color space is represented as a triangle whose vertices correspond to white, black, and pure color. The visibility of low-light image is improved by applying a modified gamma transform to the combination coefficients on an equi-hue plane in RGB color space. The contrast of the image is enhanced by the histogram specification method using the histogram smoothed by a filter with a kernel determined based on a gamma distribution. In the experiments, the effectiveness of the proposed method is verified by the comparison with the state-of-the-art low-light image enhancement methods.
Gouki OKADA Makoto NAKASHIZUKA
This paper presents a deep network based on unrolling the diffusion process with the morphological Laplacian. The diffusion process is an iterative algorithm that can solve the diffusion equation and represents time evolution with Laplacian. The diffusion process is applied to smoothing of images and has been extended with non-linear operators for various image processing tasks. In this study, we introduce the morphological Laplacian to the basic diffusion process and unwrap to deep networks. The morphological filters are non-linear operators with parameters that are referred to as structuring elements. The discrete Laplacian can be approximated with the morphological filters without multiplications. Owing to the non-linearity of the morphological filter with trainable structuring elements, the training uses error back propagation and the network of the morphology can be adapted to specific image processing applications. We introduce two extensions of the morphological Laplacian for deep networks. Since the morphological filters are realized with addition, max, and min, the error caused by the limited bit-length is not amplified. Consequently, the morphological parts of the network are implemented in unsigned 8-bit integer with single instruction multiple data set (SIMD) to achieve fast computation on small devices. We applied the proposed network to image completion and Gaussian denoising. The results and computational time are compared with other denoising algorithm and deep networks.
Tu NGUYEN VAN Satoshi YAGITANI Kensuke SHIMIZU Shinjiro NISHI Mitsunori OZAKI Tomohiko IMACHI
A metasurface absorber capable of monitoring two-dimensional (2-d) electric field distributions has been developed, where a matrix of lumped resistors between surface patches formed on a mushroom-type structure works as a 2-d array of short dipole sensors. In this paper absorption and reflection of a spherical wave incident on the metasurface absorber are analyzed by numerical computation by the plane-wave spectrum (PWS) technique using 2-d Fourier analysis. The electromagnetic field of the spherical wave incident on the absorber surface is expanded into a large number of plane waves, for each of which the TE and TM reflection and absorption coefficients are applied. Then by synthesizing all the plane wave fields we obtain the spatial distributions of reflected and absorbed fields. The detailed formulation of the computation is described, and the computed field distributions are compared with those obtained by simulation and actual measurement when the spherical wave from a dipole is illuminated onto a metasurface absorber. It is demonstrated that the PWS technique is effective and efficient in obtaining the accurate field distributions of the spherical wave on and around the absorber. This is useful for evaluating the performance of the metasurface absorber to absorb and measure the spherical wave field distributions around an EM source.
Ryoya HONDA Minoru MIZUTANI Masaya TAMURA Takashi OHIRA
This paper formulates a class-E synchronous RF rectifier from a new viewpoint. The key point is to introduce a matrix and convolute the DC terms into RF matrices. The explicit expression of input impedance is demonstrated in plane geometry. We find out their input impedance exhibits a geodesic arc in hyperbolic geometry under ZVS operation, where the theoretical RF-DC conversion efficiency results in 100%. We verify the developed theory both numerically (circuit simulation) and experimentally (6.78MHz, 100W). We confirm that the input impedance becomes a geodesic arc for a wide range of DC load resistance. The presented theory is quite elegant since it is based on a matrix-based formulation and plane-geometrical expression.
Satoshi FUJII Jun FUKUSHIMA Hirotsugu TAKIZAWA
The generation and reduction reaction of magnesium plasma were studied using a cylindrical transverse magnetic-mode applicator in magnetic and electric field modes. By heating Mg powder using the magnetic field mode, plasma was generated with the evaporation of Mg and stably sustained. When the Mg plasma sample was introduced into the reaction zone and exposed to microwave and lamp heating, a reduction reaction of scandium oxide also occurred. The results of this study provide prospects for the development of a larger microwave refining system.
This paper proposes a virtual network function (VNF) placement model considering both availability and probabilistic protection for the service delay to minimize the service deployment cost. Both availability and service delay are key requirements of services; a service provider handles the VNF placement problem with the goal of minimizing the service deployment cost while meeting these and other requirements. The previous works do not consider the delay of each route which the service can take when considering both availability and delay in the VNF placement problem; only the maximum delay was considered. We introduce probabilistic protection for service delay to minimize the service deployment cost with availability. The proposed model considers that the probability that the service delay, which consists of networking delay between hosts and processing delay in each VNF, exceeds its threshold is constrained within a given value; it also considers that the availability is constrained within a given value. We develop a two-stage heuristic algorithm to solve the VNF placement problem; it decides primary VNF placement by solving mixed-integer second-order cone programming in the first stage and backup VNF placement in the second stage. We observe that the proposed model reduces the service deployment cost compared to a baseline that considers the maximum delay by up to 12%, and that it obtains a feasible solution while the baseline does not in some examined situations.
Joong-Won SHIN Masakazu TANUMA Shun-ichiro OHMI
In this research, we investigated the threshold voltage (VTH) control by partial polarization of metal-ferroelectric-semiconductor field-effect transistors (MFSFETs) with 5 nm-thick nondoped HfO2 gate insulator utilizing Kr-plasma sputtering for Pt gate electrode deposition. The remnant polarization (2Pr) of 7.2 μC/cm2 was realized by Kr-plasma sputtering for Pt gate electrode deposition. The memory window (MW) of 0.58 V was realized by the pulse amplitude and width of -5/5 V, 100 ms. Furthermore, the VTH of MFSFET was controllable by program/erase (P/E) input pulse even with the pulse width below 100 ns which may be caused by the reduction of leakage current with decreasing plasma damage.
Ying JI Yu WANG Kensaku MORI Jien KATO
Social relationships (e.g., couples, opponents) are the foundational part of society. Social relation atmosphere describes the overall interaction environment between social relationships. Discovering social relation atmosphere can help machines better comprehend human behaviors and improve the performance of social intelligent applications. Most existing research mainly focuses on investigating social relationships, while ignoring the social relation atmosphere. Due to the complexity of the expressions in video data and the uncertainty of the social relation atmosphere, it is even difficult to define and evaluate. In this paper, we innovatively analyze the social relation atmosphere in video data. We introduce a Relevant Visual Concept (RVC) from the social relationship recognition task to facilitate social relation atmosphere recognition, because social relationships contain useful information about human interactions and surrounding environments, which are crucial clues for social relation atmosphere recognition. Our approach consists of two main steps: (1) we first generate a group of visual concepts that preserve the inherent social relationship information by utilizing a 3D explanation module; (2) the extracted relevant visual concepts are used to supplement the social relation atmosphere recognition. In addition, we present a new dataset based on the existing Video Social Relation Dataset. Each video is annotated with four kinds of social relation atmosphere attributes and one social relationship. We evaluate the proposed method on our dataset. Experiments with various 3D ConvNets and fusion methods demonstrate that the proposed method can effectively improve recognition accuracy compared to end-to-end ConvNets. The visualization results also indicate that essential information in social relationships can be discovered and used to enhance social relation atmosphere recognition.
In a convex grid drawing of a plane graph, all edges are drawn as straight-line segments without any edge-intersection, all vertices are put on grid points and all facial cycles are drawn as convex polygons. A plane graph G has a convex drawing if and only if G is internally triconnected, and an internally triconnected plane graph G has a convex grid drawing on an (n-1) × (n-1) grid if either G is triconnected or the triconnected component decomposition tree T(G) of G has two or three leaves, where n is the number of vertices in G. An internally triconnected plane graph G has a convex grid drawing on a 2n × 2n grid if T(G) has exactly four leaves. Furthermore, an internally triconnected plane graph G has a convex grid drawing on a 20n × 16n grid if T(G) has exactly five leaves. In this paper, we show that an internally triconnected plane graph G has a convex grid drawing on a 10n × 5n grid if T(G) has exactly five leaves. We also present a linear-time algorithm to find such a drawing.
Koichi MAEZAWA Umer FAROOQ Masayuki MORI
A novel displacement sensor was proposed based on a frequency delta-sigma modulator (FDSM) employing a microwave oscillator. To demonstrate basic operation, we fabricated a stylus surface profiler using a cylindrical cavity resonator, where one end of the cavity is replaced by a thin metal diaphragm with a stylus probe tip. Good surface profile was successfully obtained with this device. A 10 nm depth trench was clearly observed together with a 10 µm trench in a single scan without gain control. This result clearly demonstrates an extremely wide dynamic range of the FDSM displacement sensors.
Wentao LYU Di ZHOU Chengqun WANG Lu ZHANG
In this paper, we present a novel discriminative dictionary learning (DDL) method for image classification. The local structural relationship between samples is first built by the Laplacian eigenmaps (LE), and then integrated into the basic DDL frame to suppress inter-class ambiguity in the feature space. Moreover, in order to improve the discriminative ability of the dictionary, the category label information of training samples is formulated into the objective function of dictionary learning by considering the discriminative promotion term. Thus, the data points of original samples are transformed into a new feature space, in which the points from different categories are expected to be far apart. The test results based on the real dataset indicate the effectiveness of this method.
Dai TAGUCHI Takaaki MANAKA Mitsumasa IWAMOTO
Triboelectric generators have been attracting much attention as electrical power sources in scientific communities and industries. Based on dielectric physics, two microscopic routes are available as current sources: One is charge displacement and the other is dipolar rotation. We have been investigating these routes as power sources for triboelectric generation. In other words, dipolar energy transfer process during a course of depolarization has the potentiality to be utilized as triboelectric generator. In this paper, we show that polyimide polymer film with permanent dipoles, i.e., PMDA-ODA polyimide, can provide current source capacity enhanced at elevated temperature, which is in good agreement with our idea based on dipolar energy mode of triboelectric generator. That is, permanent dipoles rotate quickly at elevated temperature, and act as an enhanced current source in the dipolar energy source model of triboelectric generator.
Ryusuke IGARASHI Ryo NAKAGAWA Dan OKOCHI Yukio OGAWA Mianxiong DONG Kaoru OTA
Vehicles on the road are expected to connect continuously to the Internet at sufficiently high speeds, e.g., several Mbps or higher, to support multimedia applications. However, even when passing through a well-facilitated city area, Internet access can be unreliable and even disconnected if the travel speed is high. We therefore propose a network path selection technique to meet network throughput requirements. The proposed technique is based on the attractor selection model and enables vehicles to switch the path from a route connecting directly to a cellular network to a relay type through neighboring vehicles for Internet access. We also develop a mechanism that prevents frequent path switching when the performance of all available paths does not meet the requirements. We conduct field evaluations by platooning two vehicles in a real-world driving environment and confirm that the proposed technique maintains the required throughput of up to 7Mbps on average. We also evaluated our proposed technique by extensive computer simulations of up to 6 vehicles in a platoon. The results show that increasing platoon length yields a greater improvement in throughput, and the mechanism we developed decreases the rate of path switching by up to 25%.
Daiki SAITO Jeyeon KIM Tetsuya MANABE
Currently, the proportion of independent travel is increasing in Japan. Therefore, earlier studies supporting itinerary planning have been presented. However, these studies have only insufficiently considered rural tourism. For example, tourist often use public transportation during trips in rural areas, although it is often difficult for a tourist to plan an itinerary for public transportation. Even if an itinerary can be planned, it will entail long waiting times at the station or bus stop. Nevertheless, earlier studies have only insufficiently considered these elements in itinerary planning. On the other hand, navigation is necessary in addition to itinerary creation. Particularly, recent navigation often considers dynamic information. During trips using public transportation, schedule changes are important dynamic information. For example, tourist arrive at bus stop earlier than planned. In such case, the waiting time will be longer than the waiting time included in the itinerary. In contrast, if a person is running behind schedule, a risk arises of missing bus. Nevertheless, earlier studies have only insufficiently considered these schedule changes. In this paper, we construct a tourism application that considers the waiting time to improve the tourism experience in rural areas. We define waiting time using static waiting time and dynamic waiting time. Static waiting time is waiting time that is included in the itinerary. Dynamic waiting time is the waiting time that is created by schedule changes during a trip. With this application, static waiting times is considered in the planning function. The dynamic waiting time is considered in the navigation function. To underscore the effectiveness of this application, experiments of the planning function and experiments of the navigation function is conducted in Tsuruoka City, Yamagata Prefecture. Based on the results, we confirmed that a tourist can readily plan a satisfactory itinerary using the planning function. Additionally, we confirmed that Navigation function can use waiting times effectively by suggesting additional tourist spots.
Yoshihiro NAKA Masahiko NISHIMOTO Mitsuhiro YOKOTA
An efficient bent waveguide and an optical power splitter with a resonator constructed by a metal-dielectric-metal plasmonic waveguide have been analyzed. The method of solution is the finite difference time domain (FD-TD) method with the piecewise linear recursive convolution (PLRC) method. The resonator can be realized by utilizing impedance mismatch at the connection between a narrow waveguide and an input/output waveguide. Numerical results for the bent waveguide show that transmission bands can be controlled by adjusting the length of the narrow waveguide. We have also shown that the optical power of the power splitter is entirely distributed into the output waveguide at the resonant wavelength and its distribution ratio can be controlled.
Masaki HAMAMOTO Hiroyuki NAMBA Masashi EGI
Explainable artificial intelligence (AI) technology enables us to quantitatively analyze the whole prediction logic of AI as a global explanation. However, unwanted relationships learned by AI due to data sparsity, high dimensionality, and noise are also visualized in the explanation, which deteriorates confidence in the AI. Thus, methods for correcting those unwanted relationships in explanation has been developed. However, since these methods are applicable only to differentiable machine learning (ML) models but not to non-differentiable models such as tree-based models, they are insufficient for covering a wide range of ML technology. Since these methods also require re-training of the model for correcting its explanation (i.e., in-processing method), they cannot be applied to black-box models provided by third parties. Therefore, we propose a method called ensemble-based explanation correction (EBEC) as a post-processing method for correcting the global explanation of a prediction model in a model-agnostic manner by using the Rashomon effect of statistics. We evaluated the performance of EBEC with three different tasks and analyzed its function in more detail. The evaluation results indicate that EBEC can correct global explanation of the model so that the explanation aligns with the domain knowledge given by the user while maintaining its accuracy. EBEC can be extended in various ways and combined with any method to improve correction performance since it is a post-processing-type correction method. Hence, EBEC would contribute to high-productivity ML modeling as a new type of explanation-correction method.